Title: Solutions to two problems on Bandit Models
Speaker: Michael N. Katehakis, Rutgers University.
Date: Tuesday, January 28, 2014 11:00am - 12:00pm
Location: DIMACS Center, CoRE Bldg, Room 431, Rutgers University, Busch Campus, Piscataway, NJ
After a brief survey of bandit models we present solutions to two key open problems. The first deals with the situation in which a decision to engage a process is subject to a commitment of a, possibly stochastic, number or duration of activations before a change to a different process is possible. It is shown that these activation commitments are equivalent to a more general depreciation model for which optimal policies can be constructed using propitiously defined restart in state indices. The second problems deals with the model in which outcomes from different bandits are normally distributed with unknown means and unknown variances, for which the regret increase rate can be minimized by sequential 'upper confidence bounds' based policies.
DIMACS/CCICADA Interdisciplinary Series, Complete Calendar